INDEX

Explanations

terms and measurements related to experimental conditions and treatments

oai_token-act-pair · gpt-4o-mini Triggered by @bot

quantities and decreases

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Primary

-0.51

Protein

-0.47

Internet

-0.46

 MainAxisSize

-0.44

Eye

-0.42

Mag

-0.42

cased

-0.42

 فريبيس

-0.42

Phy

-0.42

Ras

-0.42

POSITIVE LOGITS

 endwhile

0.46

новништво

0.46

 rẻ

0.45

fjspx

0.44

endpush

0.43

BeginContext

0.43

EDEFAULT

0.41

SharedDtor

0.41

govina

0.39

Климаты

0.38

Activations Density 0.210%

terms and measurements related to experimental conditions and treatments

quantities and decreases

No Comments

No Known Activations